The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this paper, we reveal the importance and benefits of introducing second-order operations into deep neural networks. We propose a novel approach named Second-Order Response Transform (SORT), which appends element-wise product transform to the linear sum of a two-branch network module. A direct advantage of SORT is to facilitate cross-branch response propagation, so that each branch can update its...
The efficient development of all-digital RF-transmitters (DRFTx) requires models that can capture the memory induced, nonlinear behavior of the circuitry. Broadband time-domain models work well for this application, although, gaining dependable model prediction errors from verification measurements is difficult. For the presented DRFTx, the model predicts output signals over the full bandwidth (DC-20...
Video image dataset is playing an essential role in design and evaluation of traffic vision methods. However, there is a longstanding difficulty that manually collecting and annotating large-scale diversified dataset from real scenes is time-consuming and prone to error. In 2016, we proposed the parallel vision methodology to tackle the issues of conventional vision computing approach in data collection,...
The contribution of this paper is to bridge the gap on understanding the mathematical structure and the computational implementation of a convolutional neural network (CNN) using a minimal model (Minimal CNN). The proposed minimal CNN is presented using a layering approach. This approach provides a concise and accessible understanding of the main mathematical operations of a CNN. Hence, it benefits...
Texture classification has been extensively studied in computer vision. Recent research shows that the combination of Fisher vector (FV) encoding and convolutional neural network (CNN) provides significant improvement in texture classification over the previous feature representation methods. However, by truncating the CNN model at the last convolutional layer, the CNN-based FV descriptors would not...
Imagery texts are usually organized as a hierarchy of several visual elements, i.e. characters, words, text lines and text blocks. Among these elements, character is the most basic one for various languages such as Western, Chinese, Japanese, mathematical expression and etc. It is natural and convenient to construct a common text detection engine based on character detectors. However, training character...
Convolutional Neural Networks (CNNs) are well established models capable of achieving state-of-the-art classification accuracy for various computer vision tasks. However, they are becoming increasingly larger, using millions of parameters, while they are restricted to handling images of fixed size. In this paper, a quantization-based approach, inspired from the well-known Bag-of-Features model, is...
The problem of transferring a deep convolutional network trained for object recognition to the task of scene image classification is considered. An embedded implementation of the recently proposed mixture of factor analyzers Fisher vector (MFA-FV) is proposed. This enables the design of a network architecture, the MFAFVNet, that can be trained in an end to end manner. The new architecture involves...
To solve deep metric learning problems and producing feature embeddings, current methodologies will commonly use a triplet model to minimise the relative distance between samples from the same class and maximise the relative distance between samples from different classes. Though successful, the training convergence of this triplet model can be compromised by the fact that the vast majority of the...
We study unsupervised learning by developing a generative model built from progressively learned deep convolutional neural networks. The resulting generator is additionally a discriminator, capable of "introspection" in a sense — being able to self-evaluate the difference between its generated samples and the given training data. Through repeated discriminative learning, desirable properties...
While fine-grained object recognition is an important problem in computer vision, current models are unlikely to accurately classify objects in the wild. These fully supervised models need additional annotated images to classify objects in every new scenario, a task that is infeasible. However, sources such as e-commerce websites and field guides provide annotated images for many classes. In this...
This paper proposes a novel approach for segmenting primary video objects by using Complementary Convolutional Neural Networks (CCNN) and neighborhood reversible flow. The proposed approach first pre-trains CCNN on massive images with manually annotated salient objects in an end-to-end manner, and the trained CCNN has two separate branches that simultaneously handle two complementary tasks, i.e.,...
Detecting actions in untrimmed videos is an important yet challenging task. In this paper, we present the structured segment network (SSN), a novel framework which models the temporal structure of each action instance via a structured temporal pyramid. On top of the pyramid, we further introduce a decomposed discriminative model comprising two classifiers, respectively for classifying actions and...
The low noise amplifier (LNA) is a significant device in RF front-end. In this paper, a straight and efficient modeling method for LNA based on the Volterra series with recursive least squares (RLS) algorithm is proposed. Instead of calculating the high nonlinearity order of Volterra kernels, the proposed method extracts the first three order Volterra kernels characterizing the memory effect to construct...
This paper introduces an ensemble model that solves the binary classification problem by incorporating the basic Logistic Regression with the two recent advanced paradigms: extreme gradient boosted decision trees (xgboost) and deep learning. To obtain the best result when integrating sub-models, we introduce a solution to split and select sets of features for the sub-model training. In addition to...
In this article, the problem of determining the significance of data features is considered. For this purpose the algorithm is proposed, which with the use of Sobol method, provides the global sensitivity indices. On the basis of these indices, the aggregated sensitivity coefficients are determined which are used to indicate significant features. Using such an information, the process of features'...
This paper describes the use of convolutional neural network(CNN) method to classify various image and photo of Indonesia ancient temple. The method itself implements Deep Learning technique designed for Computer Vision task. The idea behind CNN is image pre-processing through a stack of convolution layers to create many patterns that can be easily recognized. The result shows that the learning model...
The paper shows historical aspects of the application of computer-based information systems, providing the process of cosmonaut training for a space flight at the Gagarin Cosmonaut Training Center. These systems include: systems ensuring the operation of simulation complexes for cosmonaut training, computer-assisted instruction systems (computer-assisted simulators), databases for storing the results...
In 2013, Tams et al. proposed a method to determine directed reference points in fingerprints based on a mathematical model of typical orientation fields of tented arch type fingerprints. Although this Tented Arch Reference Point (TARP) method has been used successfully for pre-alignment in biometric cryptosystems, its accuracy does not yet ensure satisfactory error rates for single finger systems...
Duplicate Bug Detection is the problem of identifying whether a newly reported bug is a duplicate of an existing bug in the system and retrieving the original or similar bugs from the past. This is required to avoid costly rediscovery and redundant work. In typical software projects, the number of duplicate bugs reported may run into the order of thousands, making it expensive in terms of cost and...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.